def test_add_document_no_client():
event = Event(event_id='1')
document = Document('plaintext',
text="“You're no help,” he told the lime. "
"This was unfair. It was only a lime; "
"there was nothing special about it at all. "
"It was doing the best it could.")
event.add_document(document)
assert event.documents['plaintext'] == document
def test_add_document(mocker):
client = mocker.Mock(EventsClient)
event = Event(event_id='1', client=client)
document = Document('plaintext',
text="“You're no help,” he told the lime. "
"This was unfair. It was only a lime; "
"there was nothing special about it at all. "
"It was doing the best it could.")
event.add_document(document)
assert event.documents['plaintext'] == document
client.add_document.assert_called_once_with(
'1', 'plaintext', "“You're no help,” he told the lime. "
"This was unfair. It was only a lime; "
"there was nothing special about it at all. "
"It was doing the best it could.")
def test_copy_document():
e = Event()
doc = Document(document_name='first', text='The quick brown fox jumped over the lazy dog.')
e.add_document(doc)
with doc.get_labeler('some_index') as label:
label(0, 3, word='The')
label(4, 9, word='quick')
label(10, 15, word='brown')
processor = CopyDocument('first', 'second')
processor.process(e, {})
second = e.documents['second']
assert second is not None
assert second.get_label_index('some_index') == [
GenericLabel(0, 3, word='The'),
GenericLabel(4, 9, word='quick'),
GenericLabel(10, 15, word='brown')
]
def dict_to_document(document_name: str,
d: Dict,
*,
event: Optional[Event] = None) -> Document:
"""Turns a serialized dictionary into a Document.
Args:
document_name (str): The name identifier of the document on the event.
d (dict): The dictionary representation of the document.
event (~typing.Optional[Event]): An event that the document should be added to.
Returns:
Document: The deserialized Document object.
"""
document = Document(document_name=document_name, text=d['text'])
if event is not None:
event.add_document(document)
for k, v in d['label_indices'].items():
index = dict_to_label_index(d=v)
document.add_labels(k, index, distinct=index.distinct)
return document
def test_json_serializer():
event = Event(event_id='1')
event.metadata['foo'] = "bar"
document = Document('plaintext', text='Some text.')
event.add_document(document)
document.add_labels('one', [
mtap.GenericLabel(start_index=0, end_index=5, x=10),
mtap.GenericLabel(start_index=6, end_index=10, x=15)
])
document.add_labels('two', [
mtap.GenericLabel(start_index=0, end_index=25, a='b'),
mtap.GenericLabel(start_index=26, end_index=42, a='c')
])
document.add_labels('three', [
mtap.GenericLabel(start_index=0, end_index=10, foo=True),
mtap.GenericLabel(start_index=11, end_index=15, foo=False)
],
distinct=True)
with TemporaryFile('w+') as tf:
JsonSerializer.event_to_file(event, tf)
tf.flush()
tf.seek(0)
o = json.load(tf)
assert o['event_id'] == '1'
assert o['metadata']['foo'] == 'bar'
d = o['documents']['plaintext']
assert d['text'] == 'Some text.'
assert len(d['label_indices']) == 3
assert d['label_indices']['one'] == {
'json_labels': [{
'start_index': 0,
'end_index': 5,
'x': 10
}, {
'start_index': 6,
'end_index': 10,
'x': 15
}],
'distinct':
False
}
assert d['label_indices']['two'] == {
'json_labels': [{
'start_index': 0,
'end_index': 25,
'a': 'b'
}, {
'start_index': 26,
'end_index': 42,
'a': 'c'
}],
'distinct':
False
}
assert d['label_indices']['three'] == {
'json_labels': [{
'start_index': 0,
'end_index': 10,
'foo': True
}, {
'start_index': 11,
'end_index': 15,
'foo': False
}],
'distinct':
True
}